Scholarlink

Accurate electrical energy price forecasting is an essential task for the utilities and generation companies for effective energy trading in markets. It helps generation companies, utilities, and industries for proper bidding strategy and schedule production and consumption effectively in such way that risk will be minimized and profit will be maximized. In this chapter, A complete procedure for electrical energy price forecasting using an deep neural network (DNN) model is presented. To train and test DNN model, data is collected from Indian Energy Exchange (IEX) and this complete data is available at https://data.mendeley.com/datasets/v5znbkzjd4/1 . The suggested model is verified by comparison with different machine learning models, such as SVM, Random Forest, Decision Trees, and Linear Regression. Comparatively speaking, the constructed DNN model can predict the load with a lower error of 0.0024.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Electrical Energy Price Forecasting for Effective Energy Trading Using Deep Neural Networks With ADADELTA Optimizer

  • 章节

  • 发表日期：

    2025年

查看全文
  • Venkataramana Veeramsetty,
  • Nikitha Baddam,
  • Thallapalli Siddartha,
  • Surender Reddy Salkuti

摘要

Accurate electrical energy price forecasting is an essential task for the utilities and generation companies for effective energy trading in markets. It helps generation companies, utilities, and industries for proper bidding strategy and schedule production and consumption effectively in such way that risk will be minimized and profit will be maximized. In this chapter, A complete procedure for electrical energy price forecasting using an deep neural network (DNN) model is presented. To train and test DNN model, data is collected from Indian Energy Exchange (IEX) and this complete data is available at https://data.mendeley.com/datasets/v5znbkzjd4/1 . The suggested model is verified by comparison with different machine learning models, such as SVM, Random Forest, Decision Trees, and Linear Regression. Comparatively speaking, the constructed DNN model can predict the load with a lower error of 0.0024.